Lazy-k Decoding: Constrained Decoding for Information Extraction
Arthur Hemmer, Mickael Coustaty, Nicola Bartolo, Jerome Brachat, Jean-marc Ogier
Abstract
We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-k. Our findings demonstrate that constrained decoding approaches can significantly improve the models’ performances, especially when using smaller models. The Lazy-k approach allows for more flexibility between decoding time and accuracy. The code for using Lazy-k decoding can be found at https://github.com/ArthurDevNL/lazyk.- Anthology ID:
- 2023.emnlp-main.416
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6727–6736
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.416
- DOI:
- 10.18653/v1/2023.emnlp-main.416
- Cite (ACL):
- Arthur Hemmer, Mickael Coustaty, Nicola Bartolo, Jerome Brachat, and Jean-marc Ogier. 2023. Lazy-k Decoding: Constrained Decoding for Information Extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6727–6736, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Lazy-k Decoding: Constrained Decoding for Information Extraction (Hemmer et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.416.pdf